Quality Control for Small Multi Domain Industries Using Image Processing

Strategic acquisition and effective management of resources empower small industries to overcome challenges, thrive in their respective sectors, and contribute to economic growth. Scarcity of resources and the intricacy of overseeing numerous production lines present particular difficulties for small, multi-domain firms in preserving a consistent level of product quality. Conventional quality control techniques frequently struggle to adequately address existing problems. These include the initial outlay needed to establish the image processing infrastructure, the possible limits in managing intricate product variants, and the requirement for large training datasets for machine learning models. Automating and enhancing the accuracy of quality control processes can be achieved through the integration of image processing technologies. Creating and implementing a strong quality control system suited for small multi-domain enterprises is the main goal of this study. The emphasis is on using image processing techniques to improve the precision and effectiveness of quality evaluation, fault identification, and classification across various product lines.The proposed approach analyses object photos taken in a controlled environment with suitable constraints. Techniques for feature extraction and image segmentation are used to find abnormalities and flaws. Real-time quality assessment is made possible by the integration of machine learning models, which enable automated decision-making. The solution enables accurate identification of circular objects inside the images through the successful detection and classification of circles.This study is a viable solution for improving production processes because of its scalability, and accuracy in circle detection.